paper-with-me

홈 › Papers

Design Principles for Lifelong Learning AI Accelerators

2023-10-05 · Dhireesha Kudithipudi, Anurag Daram, Abdullah M. Zyarah, Fatima Tuz Zohora, James B. Aimone, Angel Yanguas-Gil, Nicholas Soures, Emre Neftci, Matthew Mattina, Vincenzo Lomonaco, Clare D. Thiem, Benjamin Epstein

Lifelong learning - an agent's ability to learn throughout its lifetime - is a hallmark of biological learning systems and a central challenge for artificial intelligence (AI). The development of lifelong learning algorithms could lead to a range of novel AI applications, but this will also require the development of appropriate hardware accelerators, particularly if the models are to be deployed on edge platforms, which have strict size, weight, and power constraints. Here, we explore the design of lifelong learning AI accelerators that are intended for deployment in untethered environments. We identify key desirable capabilities for lifelong learning accelerators and highlight metrics to evaluate such accelerators. We then discuss current edge AI accelerators and explore the future design of lifelong learning accelerators, considering the role that different emerging technologies could play.

📄 PDF Abstract BibTeX arXiv:2310.04467

Code (0)

등록된 구현이 없습니다.

Tasks

Lifelong learning

Similar Papers 제목 키워드 기반

Hardware Approximate Techniques for Deep Neural Network Accelerators: A Survey

2022-03-16 · Giorgos Armeniakos, Georgios Zervakis, Dimitrios Soudris, Jörg Henkel

Deep Neural Networks (DNNs) are very popular because of their high performance in various cognitive tasks in Machine Learning (ML). Recent advancements in DNNs have brought beyond human accuracy in many tasks, but at the…

Learning the Superpixel in a Non-iterative and Lifelong Manner

2021-03-19 · CVPR 2021 1 · Lei Zhu, Qi She, Bin Zhang, Yanye Lu 외

Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence. Although some works us…

ClusteringLifelong learning

Adaptive Synaptogenesis Implemented on a Nanomagnetic Platform

2025-04-14 · Faiyaz Elahi Mullick, Supriyo Bandyopadhyay, Rob Baxter, Tony J. Ragucci 외

The human brain functions very differently from artificial neural networks (ANN) and possesses unique features that are absent in ANN. An important one among them is "adaptive synaptogenesis" that modifies synaptic weigh…

Edge-computingHippocampusLifelong learning

Context selectivity with dynamic availability enables lifelong continual learning

2023-06-02 · Martin Barry, Wulfram Gerstner, Guillaume Bellec

"You never forget how to ride a bike", -- but how is that possible? The brain is able to learn complex skills, stop the practice for years, learn other skills in between, and still retrieve the original knowledge when ne…

Continual LearningLifelong learningTransfer Learning

Efficient Meta Lifelong-Learning with Limited Memory

2020-10-06 · EMNLP 2020 11 · ZiRui Wang, Sanket Vaibhav Mehta, Barnabás Póczos, Jaime Carbonell

Current natural language processing models work well on a single task, yet they often fail to continuously learn new tasks without forgetting previous ones as they are re-trained throughout their lifetime, a challenge kn…

Lifelong learningMulti-Task LearningQuestion Answeringtext-classification+1